考量公司財務及總體經濟因素之財務危機預警模型

Financial Distress Prediction Model Using Financial and Macroeconomic Variables

卓訓甫(Hsun-Fu Cho)

指導教授 ： 吳琮璠

國立臺灣大學/管理學院/會計學研究所/碩士(2021年)

https://doi.org/10.6342/NTU202100108

摘要

本研究探討加入總體經濟變數於公司財務危機預警模型後，是否能夠增加傳 統研究僅考量財務變數之預警模型準確度。建立模型所採用之財務危機及正常公 司樣本期間為 2013 年至 2018 年之台灣上市櫃公司，並使用 2019 年之資料以驗 證樣本外期間之模型準確度。實證結果顯示加入總體經濟變數後，預警模型準確 率以及 Pseudo R-Square 上升。此外，本研究亦發現 MPI_ratio 與財務危機發生為正向關係，亦即當製造業生產指數愈高財務危機發生機率愈高，與國外納入總體經濟變數之預警研究結論不同。
另一方面，以往財務危機之預警研究多採用配對樣本方式進行模型建構，唯使用配對樣本建構模型恐造成樣本不符母體樣態等偏差，因此本研究亦探討使用傳統單期 Logit 配對樣本以及多期 Logit 建構財務危機預警模型之模型準確度。實證結果顯示，採用多期 Logit 之模型預測能力較採用單期 Logit 之配對樣本所建構者高。

關鍵字

財務危機 ； 預警模型 ； 總體經濟變數 ； 羅吉斯迴歸模型 ； 離散時間涉險 模型

並列摘要

This paper discusses whether incorporating both macroeconomic and accounting variables in prediction model can increase the accuracy of the financial distress prediction model. In this study, all financial distress and non-financial distress firms’ samples are selected from Taiwan Economic Journal (TEJ) database. The in-sample data used to build prediction models are Taiwan listed companies during 2013-2018 and use out-sample data in 2019 to verify the prediction models accuracy. The empirical result shows that after adding macroeconomic variables in financial distress prediction model, the prediction accuracy and Pseudo R-square increase. In addition, the findings also show that the relationship between MPI_ratio and corporate financial distress to be positive while in other researches the relationship between MPI_ratio and financial distress to be negative.
On the other hand, most financial distress prediction researches used traditional matching principle. While using matching sample technique may lead to deviations such as selected samples do not follow the pattern of the actual population. Therefore, this study examines the prediction accuracy of traditional matching sample technique and multi-period sampling technique. The empirical results show that using multi- period sampling technique to construct prediction models is more accurate than using matching sample technique.

並列關鍵字

Financial distress ； Prediction model ； Macroeconomic variables ； Logistic regression ； Hazard model

參考文獻

Altman, E. I. 1968. Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy. The Journal of Finance 23 (4):589-609.

Altman, E. I. 1971. Railroad Bankruptcy Propensity. The Journal of Finance 26 (2):333-345.

Altman, E. L., and T. P. McGough. 1974. Evaluation of a company as a going concern. Journal of Accountancy 138 (6):50-57.

Argenti, J. 1976. Corporate planning and corporate collapse. Long Range Planning 9 (6):12-17.

Beaver, W. H. 1966. Financial Ratios As Predictors of Failure. Journal of Accounting Research 4:71-111.